Network Risk in Artificial Network-Flow Neural Networks with Capacities

Konferenz: ANNA '18 - Advances in Neural Networks and Applications 2018
15.09.2018 - 17.09.2018 in St. St. Konstantin and Elena Resort, Bulgaria

Tagungsband: ANNA '18

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Sgurev, Vassil (IICT-BAS, Bulgarian Academy of Sciences, Sofia, Bulgaria)
Drangajov, Stanislav (Dpt. Intelligent Systems, Assistant Professor IICT-BAS, Sofia, Bulgaria)

Introducing of risk in the artificial neural networks, based on generalized network-flow is proposed in the present work. The risk is considered as a product of the corresponding signal’s level and the probability of an adverse event, related to the signal’s distortion. A case is considered when the probability of adverse events is one and the same for all neurons. It is proved that in this case a one-to-one mapping exists between the signals’ flow and the risk flow and a series of results are achieved for those two flows, as well as such related to the network coefficients for teaching. It is proved that their minimal cuts match each other. A numerical example is given, which demonstrates the validity of the results obtained and the possibility for their applications.